Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    segments of text where people are quoting or referring to what others have said

    oai_token-act-pair · gemini-2.0-flash

    saying

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.50
    ⓧ
    -0.48
    Gemeinden
    -0.47
     Nadel
    -0.46
    ⓘ
    -0.46
    covery
    -0.46
    ఔ
    -0.45
     autorytatywna
    -0.45
     بالفعل
    -0.44
    عث
    -0.44
    POSITIVE LOGITS
     BoxFit
    0.70
    TProtocol
    0.60
     createContext
    0.53
    SuppressLint
    0.52
    StateException
    0.52
    addPreferredGap
    0.50
     iprot
    0.49
     bilinear
    0.48
    kloped
    0.47
    وردی
    0.47
    Act Density 0.758%

    No Known Activations